Triple
T22135927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mathilde |
E547027
|
entity |
| Predicate | hasDiminutive |
P456
|
FINISHED |
| Object |
Tilde
Tilde is a feminine given name used as a short form of names like Mathilde or Matilda in various European languages.
|
E1522277
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Tilde | Statement: [Mathilde, hasDiminutive, Tilde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tilde Context triple: [Mathilde, hasDiminutive, Tilde]
-
A.
Tilde
Tilde is a software development company best known for its work on open-source JavaScript tools and frameworks such as Ember.js and Yarn.
-
B.
Tinmel
Tinmel is a historic village in Morocco’s High Atlas Mountains known as the spiritual and political cradle of the Almohad dynasty and the site of the famed Tinmal Mosque.
-
C.
Tiltil
Tiltil is a small town and commune in central Chile known for its rural character and historical significance within the Santiago Metropolitan Region.
-
D.
Til
Til is the first name of Til Schweiger, a prominent German actor, filmmaker, and producer known for his roles in both German cinema and international films.
-
E.
Tyltyl
Tyltyl is the young protagonist of Maurice Maeterlinck’s play "The Blue Bird," who embarks on a magical quest in search of happiness.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tilde Triple: [Mathilde, hasDiminutive, Tilde]
Generated description
Tilde is a feminine given name used as a short form of names like Mathilde or Matilda in various European languages.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tilde Target entity description: Tilde is a feminine given name used as a short form of names like Mathilde or Matilda in various European languages.
-
A.
Tilde
Tilde is a software development company best known for its work on open-source JavaScript tools and frameworks such as Ember.js and Yarn.
-
B.
Tinmel
Tinmel is a historic village in Morocco’s High Atlas Mountains known as the spiritual and political cradle of the Almohad dynasty and the site of the famed Tinmal Mosque.
-
C.
Tiltil
Tiltil is a small town and commune in central Chile known for its rural character and historical significance within the Santiago Metropolitan Region.
-
D.
Til
Til is the first name of Til Schweiger, a prominent German actor, filmmaker, and producer known for his roles in both German cinema and international films.
-
E.
Tyltyl
Tyltyl is the young protagonist of Maurice Maeterlinck’s play "The Blue Bird," who embarks on a magical quest in search of happiness.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e3a95d88190a3bd80d9471976c3 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129b9ee54819081141c4f28e1211a |
completed | April 28, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a96f52670819083932921a9148da8 |
completed | May 18, 2026, 4:35 a.m. |
| NEDg | Description generation | batch_6a0a9adfadc08190a1899173c557c054 |
completed | May 18, 2026, 4:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a9b6566908190bd92f9b13f47f665 |
completed | May 18, 2026, 4:53 a.m. |
Created at: April 16, 2026, 8:32 p.m.